Scholarlink

In this study, we explore the application of recurrent neural network (RNN) techniques to address climate change challenges and their effects on monetary policy. Our goal is to improve forecasting accuracy for monetary policy indicators. Long Short-Term Memory (LSTM) networks, a prominent type of RNN, are particularly useful due to their ability to retain both short-term and long-term information, making them well-suited for analyzing sequential data. This research utilizes LSTM models to evaluate their effectiveness in forecasting monetary indicators based on climate-related indexes, specifically in the context of Morocco. The findings reveal that LSTM forecast accuracy varies across different types of climate and monetary indexes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LSTM Model to Predict Monetary Indexes Using Climate Data

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ouaadi Ismail,
  • El Moize Othmane,
  • Ibourk Omar

摘要

In this study, we explore the application of recurrent neural network (RNN) techniques to address climate change challenges and their effects on monetary policy. Our goal is to improve forecasting accuracy for monetary policy indicators. Long Short-Term Memory (LSTM) networks, a prominent type of RNN, are particularly useful due to their ability to retain both short-term and long-term information, making them well-suited for analyzing sequential data. This research utilizes LSTM models to evaluate their effectiveness in forecasting monetary indicators based on climate-related indexes, specifically in the context of Morocco. The findings reveal that LSTM forecast accuracy varies across different types of climate and monetary indexes.